I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
13
,
No
.
4
,
Dece
m
b
er
2
0
2
4
,
p
p
.
4
1
7
8
~
4
1
8
5
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
13
.i
4
.
p
p
4
1
7
8
-
4
1
8
5
4178
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Da
ta
-
driv
en d
ecis
io
ns
:
Arti
ficial in
t
ellig
ence
-
ba
sed
experimenta
l
v
a
lida
tion o
f
o
cean
ecos
y
stem serv
i
ces sca
le
Ro
nn
ie
F
ig
ueiredo
1,
3
,
P
edro
Ca
bra
l
2,
3
1
C
e
n
t
r
e
o
f
A
p
p
l
i
e
d
R
e
s
e
a
r
c
h
i
n
M
a
n
a
g
e
m
e
n
t
a
n
d
E
c
o
n
o
mi
c
s,
P
o
l
y
t
e
c
h
n
i
c
o
f
Le
i
r
i
a
,
Le
i
r
i
a
,
P
o
r
t
u
g
a
l
2
S
c
h
o
o
l
o
f
R
e
m
o
t
e
S
e
n
s
i
n
g
a
n
d
G
e
o
m
a
t
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
N
a
n
j
i
n
g
U
n
i
v
e
r
si
t
y
o
f
I
n
f
o
r
ma
t
i
o
n
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
N
a
n
j
i
n
g
,
C
h
i
n
a
3
N
O
V
A
I
n
f
o
r
mat
i
o
n
M
a
n
a
g
e
m
e
n
t
S
c
h
o
o
l
,
U
n
i
v
e
r
s
i
d
a
d
e
N
o
v
a
d
e
Li
s
b
o
a
,
C
a
m
p
u
s
d
e
C
a
m
p
o
l
i
d
e
,
Li
s
b
on
,
P
o
r
t
u
g
a
l
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
1
2
,
2
0
2
4
R
ev
is
ed
Ma
y
1
9
,
2
0
2
4
Acc
ep
ted
J
u
n
2
1
,
2
0
2
4
S
e
v
e
ra
l
stu
d
ies
a
d
d
re
ss
th
e
m
a
in
to
p
ic
o
f
re
se
a
rc
h
,
e
c
o
sy
ste
m
se
rv
ice
s
.
It
is
a
lso
p
ro
v
e
n
th
a
t
d
e
c
isio
n
-
m
a
k
i
n
g
in
o
rg
a
n
iza
ti
o
n
s
g
e
n
e
ra
ll
y
i
n
v
o
lv
e
s
a
d
e
c
isio
n
-
m
a
k
e
r,
wh
o
a
ss
u
m
e
s
in
te
rn
a
l
re
sp
o
n
si
b
il
it
y
f
o
r
th
e
re
su
lt
s.
Ho
we
v
e
r,
wh
e
n
th
e
d
e
c
isio
n
is
c
o
ll
e
c
ti
v
e
,
we
n
e
e
d
to
th
i
n
k
a
b
o
u
t
th
e
c
o
n
tex
t
o
f
g
o
v
e
r
n
a
n
c
e
.
Ho
w
c
a
n
we
in
c
r
e
a
se
th
e
su
sta
in
a
b
le
d
e
c
isio
n
s
o
f
o
c
e
a
n
e
c
o
sy
ste
m
se
rv
ice
s
g
o
v
e
rn
a
n
c
e
?
Wh
e
n
t
h
is
d
e
c
isio
n
is
a
p
p
li
e
d
to
o
c
e
a
n
e
c
o
sy
ste
m
se
rv
ice
s
,
in
p
a
rti
c
u
l
a
r,
we
n
e
e
d
a
p
a
ra
m
e
ter.
Th
e
r
e
fo
re
,
th
e
p
ro
p
o
s
e
d
sc
a
le
is
a
n
in
it
ial
g
u
id
e
fo
r
su
p
p
o
rt
k
e
y
d
e
c
isio
n
-
m
a
k
e
rs
d
e
c
isio
n
s
o
n
th
e
g
o
v
e
rn
a
n
c
e
o
f
o
c
e
a
n
se
r
v
ice
s
e
c
o
sy
ste
m
s.
Th
e
sc
a
le
p
r
o
p
o
sa
l
wit
h
v
a
li
d
a
ti
o
n
th
ro
u
g
h
c
las
sic
a
l
li
n
e
a
r
re
g
re
ss
io
n
,
a
n
d
su
p
p
o
rted
b
y
a
n
a
rti
ficia
l
n
e
u
ra
l
n
e
tw
o
rk
,
d
e
m
o
n
stra
tes
t
h
e
m
a
in
v
a
riab
les
t
h
a
t
in
f
lu
e
n
c
e
t
h
e
d
e
c
isio
n
a
n
d
c
o
n
tri
b
u
te t
o
p
o
ss
ib
le r
isk
m
it
ig
a
ti
o
n
s in
term
s o
f
d
e
c
isio
n
s.
K
ey
w
o
r
d
s
:
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
;
Dec
is
io
n
m
ak
er
s
;
E
co
s
y
s
tem
s
er
v
ices
;
Go
v
er
n
an
ce
;
Me
asu
r
em
en
t
;
Ocean
;
Scale
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
o
n
n
ie
Fig
u
eir
ed
o
C
en
tr
e
o
f
Ap
p
lied
R
esear
ch
in
Ma
n
ag
em
en
t a
n
d
E
c
o
n
o
m
ics,
Po
ly
tech
n
ic
o
f
L
eir
ia
L
eir
ia,
Po
r
tu
g
al
E
m
ail:
r
o
n
n
ie.
f
i
g
u
eir
ed
o
@
ip
leir
ia.
p
t
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
e
liter
atu
r
e,
th
e
“e
co
s
y
s
tem
s
er
v
ices”
h
av
e
b
ee
n
r
esear
c
h
ed
a
l
o
n
g
tim
e
f
o
r
d
if
e
r
en
ts
a
p
p
licatio
n
s
.
Fu
th
er
m
o
r
e,
th
e
“e
c
o
s
y
s
tem
s
er
v
ices”
in
th
e
“d
ec
is
io
n
s
s
ci
en
ce
”
f
ield
h
as
b
ee
n
g
r
o
win
g
s
in
ce
2
0
0
5
with
a
s
ev
er
al
s
tu
d
ies.
Ho
wev
er
,
th
e
n
u
m
b
er
o
f
s
tu
d
ie
s
in
“e
co
s
y
s
t
em
s
er
v
ices”
d
e
v
elo
p
ed
with
“d
ec
is
io
n
m
ak
i
n
g
”
ap
p
r
o
ac
h
ar
e
co
n
s
id
er
in
g
in
ef
f
icien
t
b
ec
au
s
e
d
ec
is
io
n
m
ak
in
g
p
r
o
ce
s
s
es
en
v
o
lv
e
d
m
u
ltip
le
tech
n
iq
u
es
to
s
o
lv
e
th
e
p
r
o
b
lem
o
r
p
r
o
v
id
e
th
e
s
o
l
u
tio
n
s
.
I
ts
m
ea
n
s
th
at
its
n
o
t a
s
in
g
s
o
lu
tio
n
.
C
o
n
s
id
er
in
g
th
e
ap
p
r
o
ac
h
es
s
u
r
r
o
u
n
d
in
g
o
f
o
ce
an
g
o
v
er
n
an
c
e,
th
is
to
p
ic
a
r
e
c
o
m
p
lex
an
d
i
n
f
lu
en
ce
d
b
y
m
u
ltip
le
f
ac
t
o
r
s
an
d
d
ec
is
io
n
-
m
ak
e
r
s
with
d
if
f
er
e
n
t
wo
r
ld
v
iews
an
d
in
d
iv
id
u
als
[
1
]
.
Un
d
er
s
tan
d
in
g
h
o
w
in
d
iv
id
u
al
in
ter
ests
alig
n
with
ec
o
s
y
s
tem
s
er
v
ices
wo
u
ld
allo
w
f
o
r
a
b
etter
allo
ca
tio
n
o
f
r
es
o
u
r
ce
s
an
d
p
o
s
s
ib
ly
b
etter
g
o
v
er
n
a
n
ce
i
n
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
[
2
]
.
W
h
ile
ec
o
s
y
s
tem
s
er
v
ice
d
ec
is
io
n
s
ar
e
w
id
ely
r
ec
o
g
n
ized
as
a
u
s
ef
u
l
ap
p
r
o
ac
h
f
o
r
s
o
ciety
,
alth
o
u
g
h
th
e
y
ar
e
co
n
tr
o
v
er
s
ia
l
o
n
th
e
p
ar
t
o
f
m
an
a
g
em
en
t,
t
h
eir
ass
ess
m
en
t
i
n
th
e
m
ar
in
e
en
v
ir
o
n
m
en
t is co
n
s
id
er
ed
to
lag
b
eh
in
d
th
at
o
f
te
r
r
estrial
ec
o
s
y
s
tem
s
[
3
]
.
R
ec
en
t
s
tu
d
ies
o
n
ec
o
s
y
s
tem
s
er
v
ices
s
tu
d
ies
s
h
o
w
th
at
d
ee
p
lear
n
in
g
is
ch
an
g
in
g
th
e
way
o
f
d
ec
is
io
n
s
ar
e
tak
in
g
.
As
a
r
esu
lt,
it
h
as
b
ee
n
u
s
ed
in
th
e
s
tu
d
ies
lik
e
d
etec
tio
n
o
f
r
o
ck
f
is
h
in
c
h
allen
g
in
g
u
n
d
er
wate
r
en
v
ir
o
n
m
en
ts
[
4
]
,
d
etec
tio
n
o
f
co
astal e
r
o
s
io
n
[
5
]
,
an
d
s
o
il ty
p
e
p
r
ed
ictio
n
[
6
]
.
Ad
d
itio
n
ally
,
th
e
d
ee
p
lear
n
in
g
was
u
s
ed
f
o
r
v
ar
io
u
s
p
r
o
b
lem
s
in
th
e
m
ac
h
in
e
lear
n
in
g
c
o
n
tex
t,
in
clu
d
in
g
p
r
ed
ictin
g
d
ec
is
io
n
s
,
f
o
r
ec
asti
n
g
,
a
n
d
h
y
b
r
id
m
o
d
ellin
g
ap
p
r
o
ac
h
[
7
]
.
Giv
en
th
is
co
n
tex
t,
to
g
eth
er
with
th
e
n
ee
d
f
o
r
o
ce
a
n
ec
o
s
y
s
tem
s
to
b
e
ad
eq
u
ate
an
d
ef
f
ec
tiv
e
in
ter
m
s
o
f
m
an
a
g
em
en
t
ef
f
icien
c
y
,
we
ask
ed
:
h
o
w
ca
n
we
in
cr
ea
s
e
th
e
s
u
s
tain
ab
ilit
y
o
f
d
ec
is
io
n
s
in
th
e
co
n
tex
t
o
f
g
o
v
e
r
n
an
ce
?
I
n
ad
d
itio
n
,
to
s
u
p
p
o
r
t
th
e
s
tu
d
y
we
ad
r
ess
e
two
q
u
esti
o
n
s
:
“
w
h
at
ar
e
th
e
ex
ac
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Da
ta
-
d
r
iven
d
ec
is
io
n
s
:
A
r
tifi
cia
l in
tellig
en
ce
-
b
a
s
ed
ex
p
eri
men
ta
l v
a
lid
a
tio
n
o
f
…
(
R
o
n
n
i
e
F
ig
u
eired
o
)
4179
m
ea
s
u
r
em
en
t f
ac
to
r
s
f
o
r
ass
ess
in
g
s
u
s
tain
ab
le
g
o
v
er
n
an
ce
d
ec
is
io
n
s
in
o
ce
an
ec
o
s
y
s
tem
s
er
v
ices?”
a
n
d
“
w
h
at
is
th
e
r
elatio
n
s
h
ip
b
etwe
en
th
e
(
s
ix
)
d
ec
is
io
n
v
a
r
iab
les in
o
ce
an
ec
o
s
y
s
tem
s
er
v
ices?”
T
h
is
d
o
cu
m
en
t
f
o
cu
s
es
o
n
th
e
g
r
o
win
g
in
ter
est
in
o
ce
a
n
s
er
v
ice
ec
o
s
y
s
tem
s
d
ir
ec
tly
in
v
o
lv
in
g
g
o
v
er
n
an
ce
i
n
s
u
s
tain
ab
le
d
ec
is
io
n
-
m
ak
in
g
[
8
]
.
I
n
c
o
n
tr
ast
to
th
ese
ef
f
o
r
ts
,
we
d
ev
elo
p
e
d
a
n
d
v
ali
d
ated
a
s
ca
le
to
s
u
p
p
o
r
t
k
e
y
d
ec
is
io
n
-
m
ak
e
r
s
in
th
e
g
o
v
er
n
a
n
ce
o
f
d
ec
is
io
n
co
n
tex
t.
T
h
is
s
ca
le
i
s
s
ee
n
as
a
r
eso
u
r
ce
f
o
r
ad
ap
tiv
e
g
o
v
e
r
n
an
ce
to
d
e
v
elo
p
th
e
ca
p
ac
ity
to
ca
r
r
y
o
u
t
e
co
s
y
s
tem
m
an
ag
em
en
t
an
d
is
ab
le
to
p
r
ed
ictiv
ely
ass
es
s
th
e
p
o
ten
tial
o
f
d
ec
is
io
n
s
[
9
]
.
T
h
e
s
ca
le
p
r
o
p
o
s
al
with
v
alid
atio
n
th
r
o
u
g
h
class
ical
lin
ea
r
r
eg
r
ess
io
n
[
7
]
an
d
s
u
p
p
o
r
te
d
b
y
a
n
ar
tific
ial
n
eu
r
al
n
etwo
r
k
[
8
]
d
em
o
n
s
tr
at
es
th
e
m
ain
v
ar
ia
b
les
th
at
in
f
lu
en
ce
th
e
d
ec
is
io
n
an
d
co
n
tr
ib
u
te
to
p
o
s
s
ib
le
r
is
k
m
itig
atio
n
s
in
ter
m
s
o
f
d
ec
is
io
n
s
[
9
]
i
n
o
ce
an
g
o
v
er
n
an
ce
e
co
s
y
s
tem
s
s
er
v
ices.
I
t
also
allo
ws
th
e
ac
to
r
s
in
t
h
e
ec
o
s
y
s
tem
to
co
llab
o
r
ate
b
y
in
ter
ac
tin
g
an
d
ev
alu
atin
g
in
d
iv
id
u
a
l
in
ter
ests
,
tr
an
s
f
o
r
m
in
g
th
em
in
to
co
llectiv
e
i
n
ter
ests
[
1
0
]
.
I
n
th
is
way
,
s
ca
le
h
elp
s
to
f
o
s
ter
ad
ap
tiv
e
ca
p
ac
it
y
as
d
ec
is
io
n
s
ch
an
g
e
in
d
if
f
er
e
n
t
o
ce
an
co
n
te
x
ts
.
I
t
b
r
in
g
s
m
o
r
e
v
alu
e
in
te
r
m
s
o
f
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
an
d
ap
p
licatio
n
in
th
e
f
u
tu
r
e
s
tu
d
ie
s
.
T
h
e
d
o
cu
m
e
n
t
f
o
llo
wed
d
if
f
e
r
en
t
s
ec
tio
n
s
.
I
n
th
e
s
ec
tio
n
1
i
n
tr
o
d
u
ctio
n
,
th
e
liter
atu
r
e
r
ev
i
ew
o
f
th
e
s
tu
d
y
an
d
t
h
e
q
u
esti
o
n
s
wer
e
d
em
o
n
s
tr
ated
.
I
n
s
ec
tio
n
2
m
eth
o
d
,
th
e
r
esear
ch
an
d
ex
p
er
im
e
n
tal
p
r
o
ce
d
u
r
e
was
co
n
d
u
cte
d
.
I
n
s
ec
tio
n
3
r
esu
lts
,
th
e
ex
p
er
im
en
tal
o
u
tco
m
es
we
r
e
p
r
esen
ted
.
I
n
th
e
s
ec
tio
n
4
d
i
cu
s
s
io
n
,
th
e
r
esu
lts
wer
e
r
elate
d
to
th
e
liter
atu
r
e
r
e
v
iew.
Fin
aly
,
th
e
s
ec
tio
n
5
co
n
clu
s
io
n
,
s
h
o
w
th
e
lim
itatio
n
s
,
f
u
tu
r
e
r
esear
ch
,
an
d
im
p
licatio
n
s
.
2.
M
E
T
H
O
D
T
h
e
m
eth
o
d
o
f
r
esear
ch
an
d
th
e
ex
p
e
r
im
en
tal
p
r
o
ce
d
u
r
e
wa
s
co
n
d
u
cted
f
o
llo
win
g
d
if
f
er
e
n
t
s
ec
tio
n
s
.
I
n
th
e
s
ec
tio
n
2
.
1
,
th
e
co
n
ce
p
t
an
d
in
itial d
e
v
elo
p
m
e
n
t o
f
f
ac
t
o
r
s
was in
tr
o
d
u
ce
d
.
A
f
ter
th
at,
in
th
e
s
ec
tio
n
2
.
2
,
th
e
p
r
o
ce
d
u
r
e
o
f
m
ea
s
u
r
in
g
s
c
ale
d
ev
elo
p
m
e
n
t w
as p
r
esen
te
d
.
I
n
ad
d
itio
n
,
in
th
e
s
ec
tio
n
2
.
3
th
e
d
ata
c
o
llected
p
r
o
ce
s
s
was
d
escr
ib
ed
.
T
h
e
Fig
u
r
e
1
s
h
o
w
th
e
f
lo
w
o
f
d
ev
elo
p
m
en
t,
a
n
aly
s
is
an
d
m
e
asu
r
em
en
t
p
r
o
ce
s
s
(
ex
p
er
im
e
n
tal
s
etu
p
)
.
Fig
u
r
e
1
.
Pictu
r
e
o
f
ex
p
er
im
en
tal
s
etu
p
2
.
1
.
T
he
co
ncept
a
nd
ini
t
ia
l sca
le
dev
elo
pm
ent
pro
ce
s
s
T
h
e
b
eg
in
n
in
g
o
f
th
is
s
ca
le
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
s
tar
te
d
in
(
Stu
d
y
A)
,
“E
co
s
y
s
tem
s
er
v
ices
-
ch
allen
g
es
f
o
r
f
u
tu
r
e
r
esear
ch
ap
p
licatio
n
s
”
[
f
o
r
th
co
m
i
n
g
,
2
0
2
5
]
.
Af
ter
th
at,
th
e
n
ew
p
ap
e
r
(
Stu
d
y
B
)
“Oc
ea
n
ec
o
s
y
s
tem
s
er
v
ices:
m
o
d
elin
g
a
f
ac
to
r
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
to
cr
ea
te
s
u
s
tain
ab
le
v
alu
e
f
o
r
d
ec
is
io
n
”
[
1
1
]
,
was
d
ev
elo
p
e
d
b
ased
o
n
th
e
f
in
d
s
o
f
(
Stu
d
y
A)
.
Du
r
in
g
th
is
p
er
i
o
d
,
we
f
o
llo
wed
th
e
in
itial
g
u
i
d
elin
es
p
r
o
v
id
e
d
b
y
[
1
2
]
to
d
ev
elo
p
th
r
ee
s
tep
s
o
f
th
e
Delp
h
i
m
eth
o
d
:
f
ac
to
r
g
e
n
er
atio
n
,
f
ac
to
r
r
e
d
u
ctio
n
an
d
f
ac
to
r
r
ef
i
n
em
en
t,
in
clu
d
in
g
th
e
d
o
m
ai
n
s
(
Stu
d
y
B
)
.
An
d
,
we
f
o
llo
wed
th
e
co
m
p
lem
en
tar
y
s
tep
s
p
r
o
v
id
ed
b
y
[
1
3
]
to
d
ev
elo
p
th
e
co
n
s
tr
u
cts
an
d
p
r
o
ce
d
u
r
es
f
o
r
v
alid
atio
n
.
I
n
th
is
p
ap
er
(
Stu
d
y
C
)
,
“Da
ta
-
d
r
iv
en
d
ec
is
io
n
s
:
ar
tific
ial
in
tellig
en
ce
(
AI
)
-
b
ased
ex
p
er
im
en
tal
v
ali
d
atio
n
o
f
o
ce
a
n
ec
o
s
y
s
tem
s
er
v
ices
s
ca
le
”
we
v
alid
ate
a
s
ca
le
f
o
r
s
u
s
tain
ab
le
g
o
v
er
n
an
ce
d
ec
is
io
n
s
in
ec
o
s
y
s
tem
s
er
v
ices m
an
ag
em
en
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
13
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
1
7
8
-
4
1
8
5
4180
2
.
2
.
T
he
pro
ce
du
re
o
f
m
e
a
s
urem
ent
s
ca
le
dev
elo
pm
ent
T
h
e
f
ac
to
r
s
wer
e
d
esig
n
e
d
to
f
o
llo
w
m
u
ltip
le
-
item
s
ca
les
(
lik
er
t
s
ca
le/s
ev
en
p
o
in
ts
)
.
T
h
e
m
e
asu
r
em
en
t
d
ev
elo
p
m
e
n
t
p
r
o
ce
s
s
was
co
n
d
u
cted
ac
co
r
d
in
g
t
o
th
e
“f
a
cto
r
g
e
n
er
atio
n
”,
“f
ac
to
r
r
ed
u
ctio
n
”
an
d
“f
ac
to
r
r
ef
in
em
en
t”
(
Stu
d
y
B
)
a
n
d
in
cl
u
d
ed
p
r
o
ce
d
u
r
es
o
f
v
alid
atio
n
:
i)
“d
ata
co
llectio
n
”,
“e
x
p
l
o
r
ato
r
y
f
ac
t
o
r
an
aly
s
is
”
an
d
“Cro
n
b
ac
h
’
s
al
p
h
a”
;
ii)
“d
ata
co
llectio
n
”,
“c
o
r
r
elatio
n
an
aly
s
is
”,
ex
p
lo
r
ato
r
y
f
ac
to
r
an
aly
s
is
”,
“Cro
n
b
ac
h
’
s
alp
h
a”
,
r
eg
r
ess
io
n
m
o
d
el
an
d
a
r
tific
ial
n
eu
r
al
n
etwo
r
k
”
[
1
4
]
.
T
h
e
s
tep
s
h
elp
u
s
to
s
u
p
p
o
r
t
th
e
two
wav
es
o
f
d
ata
co
llectio
n
p
r
o
ce
d
u
r
e:
f
ir
s
t q
u
e
s
tio
n
n
air
e
an
d
s
ec
o
n
d
q
u
esti
o
n
n
air
e.
2
.
3
.
T
he
da
t
a
c
o
llect
io
n pro
ce
du
re
T
o
co
llect
th
e
e
m
p
ir
ical
d
ata,
o
u
r
s
tu
d
y
em
p
lo
y
e
d
a
p
r
o
f
es
s
io
n
al
r
esear
ch
co
m
p
a
n
y
to
c
o
llect
th
e
r
eq
u
ir
ed
d
ata
f
r
o
m
s
tak
eh
o
ld
e
r
s
in
v
o
lv
ed
i
n
th
e
ec
o
s
y
s
tem
s
er
v
ices
f
ield
.
T
h
e
in
v
itatio
n
w
as
s
en
t
to
a
r
an
d
o
m
s
am
p
le
o
f
s
tak
eh
o
l
d
er
s
[
1
5
]
(
Stu
d
y
B
)
.
T
h
e
d
ata
wer
e
co
lle
cted
at
two
d
if
f
e
r
en
t
tim
e
p
o
i
n
ts
.
I
n
ad
d
itio
n
,
we
s
elec
ted
r
esp
o
n
d
en
ts
wh
o
wer
e
d
em
o
g
r
a
p
h
ically
s
im
ilar
to
th
e
p
o
p
u
latio
n
to
r
ed
u
ce
b
ias
in
th
e
s
am
p
le
[
1
4
]
.
Fin
ally
,
th
e
I
P
ad
d
r
ess
was
u
s
ed
to
c
h
ec
k
an
d
v
alid
ate
a
u
n
iq
u
e
r
esp
o
n
d
en
t
a
n
d
p
r
e
v
en
t
r
esp
o
n
s
es
f
r
o
m
th
e
s
am
e
s
tak
eh
o
ld
er
.
I
n
th
e
f
ir
s
t
wav
e
,
a
to
tal
o
f
1
,
2
0
0
s
tak
eh
o
ld
er
s
ac
ce
s
s
ed
t
h
e
li
n
k
,
a
n
o
n
lin
e
s
u
r
v
ey
,
with
4
8
0
r
esp
o
n
s
es
to
th
e
v
ar
iab
les
d
escr
ib
ed
i
n
Stu
d
y
B
.
Af
ter
th
at,
we
r
em
o
v
ed
th
e
m
is
s
in
g
d
ata,
a
n
d
4
4
2
r
esp
o
n
s
es
wer
e
co
n
s
id
er
ed
v
alid
f
o
r
f
u
tu
r
e
an
a
ly
s
is
.
I
ts
h
elp
u
s
to
m
o
v
e
t
o
th
e
s
ec
o
n
d
wav
e.
I
n
th
e
s
ec
o
n
d
wav
e,
af
ter
th
r
ee
wee
k
s
,
th
e
s
am
e
r
esp
o
n
d
e
n
ts
wer
e
in
v
ited
to
co
m
p
lete
th
e
s
ec
o
n
d
q
u
esti
o
n
n
air
e
ag
ai
n
.
A
to
tal
o
f
3
2
8
r
esp
o
n
d
en
ts
wer
e
v
alid
f
o
r
an
aly
s
is
,
f
o
r
a
g
r
o
s
s
r
esp
o
n
s
e
r
ate
o
f
7
4
%.
T
h
e
u
n
it
o
f
an
aly
s
is
o
f
o
u
r
s
tu
d
y
was
s
ev
er
al
o
r
g
an
iz
atio
n
s
co
n
n
ec
ted
with
th
e
ec
o
s
y
s
tem
s
er
v
ices
f
ield
.
T
h
e
r
esp
o
n
d
en
ts
s
h
o
u
ld
b
e
k
n
o
wl
ed
g
ea
b
le
ab
o
u
t
th
e
b
u
s
in
ess
an
d
k
ey
-
d
ec
is
io
n
m
ak
er
p
r
o
f
ile.
T
h
e
s
tati
s
tical
p
ac
k
ag
e
f
o
r
th
e
s
o
cial
s
cien
ce
s
(
SPSS
)
s
o
f
twar
e
(
v
.
2
9
)
was
u
s
ed
o
n
th
e
an
aly
s
is
[
1
6
]
.
3.
RE
SU
L
T
S
3
.1
.
Ana
ly
s
is
o
f
t
he
f
irst
wa
v
e
(
s
ca
le
pu
rif
ica
t
io
n a
nd
ini
t
i
a
l v
a
lid
a
t
io
n)
3
.
1
.
1
.
E
x
plo
ra
t
o
ry
f
a
ct
o
r
a
n
a
ly
s
is
T
h
e
Kaiser
‒
Me
y
er
‒
Olk
in
(
K
MO
)
test
was
u
s
ed
t
o
th
e
s
am
p
lin
g
a
d
eq
u
ac
y
to
r
e
d
u
ce
th
e
r
ed
u
n
d
an
cy
o
f
th
e
c
o
n
s
tr
u
cts
to
s
h
o
w
th
e
ir
v
alid
ity
.
T
h
e
r
esu
lts
(
.
9
4
7
*
)
p
r
esen
t
a
n
u
m
b
er
o
f
m
ea
s
u
r
es
h
ig
h
er
t
h
an
0
.
5
(
co
m
m
u
n
alities
)
,
in
d
icatin
g
th
at
f
ac
to
r
an
aly
s
is
ca
n
b
e
u
s
ef
u
l
f
o
r
th
e
v
ar
iab
ilit
y
o
f
th
e
v
ar
ia
b
le.
I
n
ter
m
s
o
f
t
h
e
h
ig
h
co
r
r
elatio
n
b
etwe
en
th
e
v
ar
iab
les,
B
ar
tlett´s
te
s
t
o
f
s
p
h
er
icity
s
h
o
ws
a
s
ig
n
if
ican
t
i
m
p
ac
t
o
n
th
e
n
u
m
b
er
o
f
v
ar
iab
les
s
u
itab
le
f
o
r
f
ac
t
o
r
an
aly
s
is
(
>5
/Si
g
.
<,
0
0
1
)
[
1
7
]
.
T
h
e
f
ac
to
r
lo
a
d
in
g
f
o
r
ea
ch
co
n
s
tr
u
ct
r
an
g
e
d
b
etwe
en
5
7
5
a
n
d
9
0
3
,
in
d
icatin
g
g
o
o
d
v
alid
ity
o
f
th
e
c
o
n
s
tr
u
cts.
T
h
e
to
tal
v
ar
ian
ce
ex
p
lain
e
d
was
7
8
%.
Fin
ally
,
p
r
in
cip
al
co
m
p
o
n
en
t
a
n
aly
s
is
an
d
t
h
e
v
a
r
im
ax
with
Kais
er
n
o
r
m
aliza
tio
n
s
h
o
w
th
at
t
h
e
1
4
in
ter
ac
ti
o
n
s
co
n
v
er
g
ed
in
ter
m
s
o
f
r
o
tatio
n
[
1
8
]
.
T
h
e
f
ac
to
r
s
GOV1
1
a
n
d
GOV1
2
wer
e
ex
clu
d
ed
f
r
o
m
th
e
an
aly
s
is
.
Af
ter
th
e
f
ac
to
r
s
wer
e
r
etested
in
t
h
e
“
an
aly
s
is
o
f
s
ec
o
n
d
wav
e
”
s
ec
tio
n
[
1
9
]
.
3
.
1
.
2
.
I
nte
rna
l
co
ns
is
t
ency
re
lia
bil
it
y
a
na
ly
s
is
-
cr
o
nb
a
ch´
s
t
est
I
n
ter
n
al
c
o
n
s
is
ten
cy
r
ef
e
r
s
to
t
h
e
r
eliab
ilit
y
o
f
a
s
u
m
m
ated
s
ca
le
in
wh
ich
s
ev
er
al
item
s
ar
e
s
u
m
m
ed
to
ca
lcu
late
a
to
tal
s
co
r
e.
T
h
e
in
ter
n
al
co
n
s
is
ten
cy
r
esu
lts
(
.
9
7
5
)
ac
c
o
r
d
in
g
to
th
e
v
alu
e
o
f
C
r
o
n
b
ac
h
´
s
test
(
α
>.
7
)
[
2
0
]
.
T
h
e
f
in
al
co
n
s
tr
u
c
ts
ar
e
s
u
m
m
ar
ized
in
T
a
b
le
1
.
3
.
2
.
Ana
ly
s
is
o
f
t
he
s
ec
o
nd
wa
v
e
(
m
e
a
s
urem
ent
s
ca
le
a
n
d a
na
ly
s
is
)
3
.
2
.
1
.
Co
rr
ela
t
io
n
a
na
ly
s
is
T
h
e
s
ec
o
n
d
wav
e
was
d
ed
icate
d
to
r
ep
r
esen
tin
g
a
c
o
n
s
tr
u
ct
-
to
-
f
ac
to
r
m
ea
s
u
r
e
s
ca
le
[
2
1
]
.
W
e
p
r
o
p
o
s
ed
th
e
f
ac
to
r
co
r
r
elatio
n
(
item
-
to
-
to
tal)
m
eth
o
d
to
m
ea
s
u
r
e
c
o
n
s
tr
u
ct
v
alid
ity
[
2
2
]
.
T
h
e
r
esu
lts
in
d
icate
d
t
h
at
th
e
co
r
r
elatio
n
an
al
y
s
is
was
p
o
s
it
iv
e,
f
r
o
m
m
o
d
e
r
ate
to
s
tr
o
n
g
an
d
s
ig
n
if
ican
t
f
o
r
all
th
e
f
o
l
lo
win
g
co
n
s
tr
u
cts:
g
o
v
er
n
an
ce
(
R
:
1
)
,
p
e
o
p
le
(
R
:
+
.
6
0
5
*
)
,
p
la
n
et
(
R
:
+
.
7
5
0
*
)
,
cu
ltu
r
al
(
R
:
+
.
6
4
2
*
)
,
an
d
s
p
atial
(
R
:
+
.
6
0
3
*
)
.
T
h
e
co
n
f
id
en
ce
in
ter
v
al
was
9
5
%,
an
d
th
e
esti
m
atio
n
was
b
a
s
ed
o
n
Fis
h
er
'
s
r
-
to
-
z
tr
an
s
f
o
r
m
atio
n
with
b
ias
ad
ju
s
tm
en
t
[
2
3
]
.
3
.
2
.
2
.
E
x
plo
ra
t
o
ry
f
a
ct
o
r
a
n
a
ly
s
is
T
h
e
KM
O
r
esu
lts
(
.
9
5
2
*
)
p
r
esen
t
th
e
n
u
m
b
er
o
f
m
ea
s
u
r
es
h
ig
h
er
th
a
n
0
.
5
(
co
m
m
u
n
alities
)
,
in
d
icatin
g
th
at
f
ac
to
r
an
aly
s
is
ca
n
b
e
u
s
ef
u
l
f
o
r
th
e
v
ar
iab
ilit
y
o
f
th
e
v
ar
iab
le.
B
ar
tlett´s
te
s
t
o
f
s
p
h
er
icity
r
ev
ea
led
a
s
ig
n
if
ican
t
im
p
ac
t
o
n
th
e
n
u
m
b
er
o
f
v
a
r
iab
les
s
u
itab
le
f
o
r
f
ac
to
r
an
aly
s
is
(
>5
/Si
g
.
<
.
0
0
1
)
[
2
4
]
.
T
h
e
f
ac
to
r
lo
ad
in
g
f
o
r
ea
ch
c
o
n
s
tr
u
ct
r
a
n
g
ed
b
etwe
en
5
8
1
a
n
d
9
0
8
,
in
d
icatin
g
g
o
o
d
v
alid
ity
o
f
th
e
co
n
s
tr
u
cts.
T
h
e
to
tal
v
ar
ian
ce
ex
p
lain
ed
was th
e
s
a
m
e,
at
7
8
%
[
1
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Da
ta
-
d
r
iven
d
ec
is
io
n
s
:
A
r
tifi
cia
l in
tellig
en
ce
-
b
a
s
ed
ex
p
eri
men
ta
l v
a
lid
a
tio
n
o
f
…
(
R
o
n
n
i
e
F
ig
u
eired
o
)
4181
T
ab
le
1
.
Scale
p
r
o
p
er
ties
o
f
t
h
e
m
ea
s
u
r
em
en
t m
o
d
el
V
a
r
i
a
b
l
e
F
a
c
t
o
r
s
G
O
V
ER
N
A
N
C
E
G
O
V
1
:
S
u
c
c
e
ssf
u
l
a
d
a
p
t
a
t
i
o
n
e
n
t
a
i
l
s
st
e
e
r
i
n
g
p
r
o
c
e
ss
e
s
o
f
c
h
a
n
g
e
t
h
r
o
u
g
h
i
n
st
i
t
u
t
i
o
n
s,
i
n
t
h
e
i
r
b
r
o
a
d
e
s
t
se
n
se
.
G
O
V
2
:
T
h
e
g
o
v
e
r
n
a
n
c
e
o
f
a
d
a
p
t
a
t
i
o
n
i
s
c
o
n
c
e
r
n
e
d
w
i
t
h
i
ss
u
e
s
o
f
e
q
u
i
t
y
i
n
t
h
e
o
u
t
c
o
mes
o
f
e
n
v
i
r
o
n
me
n
t
a
l
d
e
c
i
si
o
n
-
ma
k
i
n
g
.
G
O
V
3
:
C
o
m
p
r
e
h
e
n
si
v
e
u
n
d
e
r
s
t
a
n
d
i
n
g
i
s
a
c
h
i
e
v
e
d
b
y
o
p
e
n
,
sh
a
r
e
d
i
n
f
o
r
mat
i
o
n
so
u
r
c
e
s
t
h
a
t
f
i
l
l
g
a
p
s
a
n
d
f
a
c
i
l
i
t
a
t
e
i
n
t
e
g
r
a
t
i
o
n
.
G
O
V
4
:
C
r
o
ss
-
se
c
t
o
r
a
l
a
n
a
l
y
si
s
i
d
e
n
t
i
f
i
e
s
e
mer
g
e
n
t
p
r
o
b
l
e
ms
a
n
d
i
n
t
e
g
r
a
t
e
s
p
o
l
i
c
y
i
m
p
l
e
me
n
t
a
t
i
o
n
.
G
O
V
5
:
F
l
e
x
i
b
l
e
a
n
d
r
e
s
p
o
n
s
i
v
e
t
o
c
h
a
n
g
e
.
G
O
V
6
:
F
o
c
u
se
d
h
o
l
i
s
t
i
c
a
l
l
y
o
n
s
o
c
i
a
l
–
e
c
o
l
o
g
i
c
a
l
i
n
t
e
r
a
c
t
i
o
n
s.
G
O
V
7
:
W
e
l
l
,
i
n
f
o
r
me
d
b
y
a
d
i
v
e
r
si
t
y
o
f
p
e
r
sp
e
c
t
i
v
e
s
.
G
O
V
8
:
R
e
f
l
e
c
t
i
v
e
i
n
d
e
c
i
si
o
n
-
ma
k
i
n
g
.
G
O
V
9
:
I
n
n
o
v
a
t
i
v
e
i
n
p
r
o
b
l
e
m
-
so
l
v
i
n
g
.
G
O
V
1
0
:
C
o
l
l
e
c
t
i
v
e
a
s
p
e
c
t
s
r
e
l
a
t
e
d
t
o
f
i
sh
i
n
g
b
e
h
a
v
i
o
r
a
n
d
a
t
t
i
t
u
d
e
s
t
h
a
t
i
n
f
l
u
e
n
c
e
f
i
s
h
e
r
m
e
n
’
s
i
n
v
o
l
v
e
m
e
n
t
i
n
l
o
c
a
l
ma
n
a
g
e
me
n
t
.
G
O
V
1
3
:
G
o
v
e
r
n
a
n
c
e
i
s
p
o
l
y
c
e
n
t
r
i
c
a
n
d
h
o
r
i
z
o
n
t
a
l
,
w
i
t
h
b
r
o
a
d
s
t
a
k
e
h
o
l
d
e
r
p
a
r
t
i
c
i
p
a
t
i
o
n
.
G
O
V
1
4
:
A
d
o
p
t
i
o
n
o
f
d
y
n
a
m
i
c
c
o
o
p
e
r
a
t
i
o
n
a
g
r
e
e
me
n
t
s
t
h
a
t
a
d
a
p
t
t
o
t
h
e
c
h
a
n
g
i
n
g
n
e
e
d
s
o
f
g
o
v
e
r
n
a
n
c
e
.
P
EO
P
LE
P
EP1
:
W
e
h
a
v
e
i
n
d
i
v
i
d
u
a
l
l
e
a
d
e
r
s
h
i
p
a
n
d
s
t
a
k
e
h
o
l
d
e
r
d
i
a
l
o
g
u
e
$
2
w
i
t
h
a
f
o
c
u
s
o
n
so
c
i
a
l
t
r
a
n
sf
o
r
m
a
t
i
o
n
.
P
EP2
:
I
t
a
l
k
t
o
my
c
o
l
l
e
a
g
u
e
s
f
r
o
m
p
o
p
u
l
a
t
i
o
n
r
e
g
i
s
t
r
y
,
r
e
g
a
r
d
i
n
g
w
h
e
r
e
n
e
w
p
e
o
p
l
e
h
a
v
e
m
o
v
e
d
i
n
.
P
EP3
:
Em
p
l
o
y
a
m
i
x
o
f
c
o
l
l
a
b
o
r
a
t
i
v
e
t
o
o
l
s
a
n
d
sp
a
c
e
s t
h
a
t
c
o
n
s
i
d
e
r
s t
h
e
sk
i
l
l
se
t
s
a
n
d
c
o
m
p
e
t
e
n
c
e
s
o
f
d
i
f
f
e
r
e
n
t
t
a
r
g
e
t
a
u
d
i
e
n
c
e
s.
P
EP4
:
En
s
u
r
e
t
h
a
t
a
d
e
q
u
a
t
e
t
r
a
i
n
i
n
g
a
n
d
su
p
p
o
r
t
a
r
e
i
n
p
l
a
c
e
t
o
t
a
c
k
l
e
e
x
i
s
t
i
n
g
b
a
r
r
i
e
r
s
t
o
i
n
c
l
u
si
v
e
c
o
c
r
e
a
t
i
o
n
p
r
o
c
e
sse
s.
P
LA
N
ET
P
LT1
:
T
h
e
me
a
su
r
a
b
l
e
a
n
d
p
e
r
c
e
i
v
e
d
i
mp
a
c
t
s
o
f
d
e
v
e
l
o
p
me
n
t
o
n
s
u
b
si
s
t
e
n
c
e
h
a
r
v
e
st
o
f
f
i
sh
.
P
LT2
:
F
i
sh
e
r
me
n
a
r
e
f
l
e
x
i
b
l
e
t
o
c
h
a
n
g
e
s
i
n
t
h
e
c
o
mm
u
n
i
t
y
a
n
d
/
o
r
t
o
n
e
w
r
u
l
e
s
d
e
f
i
n
i
n
g
u
s
e
a
n
d
a
c
c
e
ss
t
o
t
h
e
r
e
so
u
r
c
e
s
.
P
LT3
:
P
r
e
d
i
c
t
a
b
l
e
a
n
d
u
n
p
r
e
d
i
c
t
a
b
l
e
i
mp
a
c
t
s
o
f
c
l
i
m
a
t
e
c
h
a
n
g
e
a
r
e
e
x
p
e
c
t
e
d
t
o
a
f
f
e
c
t
mar
i
n
e
s
y
s
t
e
ms
a
n
d
h
a
v
e
d
i
r
e
c
t
e
f
f
e
c
t
s
o
n
f
i
s
h
s
p
e
c
i
e
s.
P
LT4
:
T
h
e
i
m
p
a
c
t
o
f
c
h
a
n
g
e
o
n
sp
e
c
i
e
s o
n
t
h
e
c
o
a
st
.
P
R
O
F
I
T
P
R
F
T1
:
F
i
n
a
n
c
i
a
l
r
e
so
u
r
c
e
s a
r
e
d
i
v
e
r
s
i
f
i
e
d
u
si
n
g
a
b
r
o
a
d
s
e
t
o
f
p
r
i
v
a
t
e
a
n
d
p
u
b
l
i
c
f
i
n
a
n
c
i
a
l
i
n
st
r
u
me
n
t
s.
P
R
F
T2
:
B
e
t
t
e
r
i
n
f
r
a
st
r
u
c
t
u
r
e
l
e
a
d
s
t
o
h
i
g
h
e
r
f
l
e
x
i
b
i
l
i
t
y
a
n
d
l
e
a
r
n
i
n
g
g
e
n
e
r
a
t
i
n
g
e
c
o
n
o
m
i
c
a
l
t
e
r
n
a
t
i
v
e
s.
P
R
F
T3
:
I
n
t
r
o
d
u
c
i
n
g
m
e
a
s
u
r
e
s
f
o
r
mi
t
i
g
a
t
i
n
g
r
e
so
u
r
c
e
sc
a
r
c
i
t
y
i
ss
u
e
s
a
n
d
e
n
s
u
r
i
n
g
t
h
e
h
u
ma
n
,
f
i
n
a
n
c
i
a
l
,
a
n
d
t
e
c
h
n
o
l
o
g
i
c
a
l
r
e
s
o
u
r
c
e
s
n
e
e
d
e
d
a
t
t
h
e
mu
n
i
c
i
p
a
l
l
e
v
e
l
t
o
s
u
p
p
o
r
t
g
o
v
e
r
n
a
n
c
e
.
C
U
LTU
R
A
L
C
U
LT
1
:
P
r
o
m
o
t
e
a
c
u
l
t
u
r
e
o
f
(
o
p
e
n
)
i
n
n
o
v
a
t
i
o
n
a
n
d
e
x
p
e
r
i
m
e
n
t
a
t
i
o
n
i
n
t
h
e
p
u
b
l
i
c
se
c
t
o
r
.
C
U
LT
2
:
M
a
k
e
t
h
e
d
e
c
i
si
o
n
-
ma
k
i
n
g
p
r
o
c
e
ss
m
o
r
e
v
i
s
i
b
l
e
t
h
r
o
u
g
h
t
h
e
u
s
e
o
f
r
e
p
o
r
t
s
.
C
U
LT
3
:
D
e
v
e
l
o
p
st
a
n
d
a
r
d
s
a
n
d
t
e
c
h
n
i
c
a
l
r
e
g
u
l
a
t
i
o
n
s f
o
r
e
c
o
s
y
s
t
e
m s
e
r
v
i
c
e
s.
C
U
LT
4
:
E
n
g
a
g
e
w
i
t
h
l
o
c
a
l
a
n
d
su
p
r
a
l
o
c
a
l
k
n
o
w
l
e
d
g
e
-
s
h
a
r
i
n
g
n
e
t
w
o
r
k
s
t
h
a
t
f
a
c
i
l
i
t
a
t
e
t
h
e
a
c
q
u
i
si
t
i
o
n
a
n
d
d
i
ss
e
mi
n
a
t
i
o
n
o
f
k
e
y
l
e
sso
n
s
o
n
g
o
v
e
r
n
a
n
c
e
d
e
c
i
si
o
n
s.
C
U
LT
5
:
M
a
n
a
g
e
i
n
n
o
v
a
t
i
o
n
p
a
r
t
n
e
r
sh
i
p
s
b
y
r
e
p
l
a
c
i
n
g
(
w
h
e
n
p
o
ssi
b
l
e
)
b
u
r
e
a
u
c
r
a
t
i
c
c
o
n
t
r
o
l
mea
s
u
r
e
s
w
i
t
h
t
r
u
s
t
-
b
a
s
e
d
mec
h
a
n
i
sms
.
C
U
LT
6
:
E
n
su
r
e
p
o
l
i
t
i
c
a
l
c
o
m
mi
t
me
n
t
a
n
d
p
u
b
l
i
c
se
c
t
o
r
l
e
a
d
e
r
sh
i
p
t
h
r
o
u
g
h
o
u
t
t
h
e
d
i
f
f
e
r
e
n
t
p
h
a
ses
o
f
smar
t
c
i
t
y
t
r
a
n
s
i
t
i
o
n
s
.
C
U
LT
7
:
I
n
t
r
o
d
u
c
e
i
n
n
o
v
a
t
i
v
e
p
r
o
c
u
r
e
me
n
t
m
e
t
h
o
d
s
,
su
c
h
a
s
l
o
n
g
-
f
l
e
x
i
b
l
e
c
o
n
t
r
a
c
t
s,
t
h
a
t
f
i
t
w
i
t
h
t
h
e
i
mp
l
e
m
e
n
t
a
t
i
o
n
r
e
q
u
i
r
e
m
e
n
t
s
o
f
o
c
e
a
n
e
c
o
sy
s
t
e
m
ser
v
i
c
e
s
p
r
o
j
e
c
t
s.
C
U
LT
8
:
N
u
r
t
u
r
e
a
n
i
n
n
o
v
a
t
i
v
e
c
u
l
t
u
r
e
a
n
d
e
x
p
e
r
i
m
e
n
t
a
t
i
o
n
i
n
t
h
e
p
u
b
l
i
c
se
c
t
o
r
.
S
P
A
TI
A
L
S
P
A
T1
:
Em
p
l
o
y
a
s
p
a
c
e
t
h
a
t
c
o
n
si
d
e
r
s t
h
e
s
k
i
l
l
s
e
t
s
a
n
d
c
o
m
p
e
t
e
n
c
e
s
o
f
d
i
f
f
e
r
e
n
t
t
a
r
g
e
t
a
u
d
i
e
n
c
e
s.
S
P
A
T2
:
D
i
sc
u
ss
d
e
c
i
s
i
o
n
s
w
i
t
h
d
i
f
f
e
r
e
n
t
n
e
i
g
h
b
o
r
h
o
o
d
s i
n
t
e
r
ms
o
f
i
m
p
a
c
t
.
S
P
A
T3
:
I
d
e
n
t
i
f
y
se
v
e
r
a
l
k
e
y
c
a
p
a
b
i
l
i
t
i
e
s
t
h
a
t
f
a
c
i
l
i
t
a
t
e
t
h
e
a
p
p
l
i
c
a
t
i
o
n
o
f
g
e
o
g
r
a
p
h
i
c
d
e
c
i
s
i
o
n
s.
S
P
A
T4
:
A
v
o
i
d
f
r
a
g
me
n
t
a
t
i
o
n
o
f
l
o
c
a
l
p
o
l
i
c
i
e
s f
o
r
t
h
e
g
o
v
e
r
n
a
n
c
e
o
f
e
c
o
s
y
s
t
e
m s
e
r
v
i
c
e
s.
S
P
A
T5
:
D
i
sc
u
ss
t
h
e
i
mp
a
c
t
o
f
b
e
i
n
g
t
o
g
e
t
h
e
r
i
n
s
p
e
c
i
f
i
c
s
p
a
c
e
s w
i
t
h
d
i
f
f
e
r
e
n
t
a
p
p
r
o
a
c
h
e
s.
S
A
P
T6
:
P
r
o
m
o
t
e
a
n
a
l
y
ses
f
o
c
u
se
d
o
n
t
h
e
r
o
l
e
o
f
a
r
e
a
,
p
l
a
c
e
,
a
n
d
l
o
c
a
t
i
o
n
.
S
P
A
T7
:
D
e
v
e
l
o
p
st
a
n
d
a
r
d
s
a
n
d
t
e
c
h
n
i
c
a
l
r
e
g
u
l
a
t
i
o
n
s
f
o
r
o
c
e
a
n
e
c
o
sy
s
t
e
m
s
e
r
v
i
c
e
s
d
a
t
a
c
o
l
l
e
c
t
i
o
n
.
S
P
A
T8
:
P
r
o
v
i
d
e
i
n
f
o
r
ma
t
i
o
n
a
b
o
u
t
t
h
e
sp
a
t
i
a
l
l
o
c
a
t
i
o
n
f
o
r
s
h
a
r
i
n
g
d
e
c
i
s
i
o
n
s.
To
t
a
l
o
f
i
t
e
ms:
3
9
3
.
2
.
3
.
I
nte
rna
l
co
ns
is
t
ency
re
lia
bil
it
y
a
na
ly
s
is
T
h
e
i
n
t
e
r
n
a
l
c
o
n
s
i
s
t
e
n
c
y
r
e
s
u
l
t
s
(
.
9
7
6
)
a
c
c
o
r
d
i
n
g
t
o
t
h
e
v
a
l
u
e
o
f
C
r
o
n
b
a
c
h
´
s
t
e
s
t
(
α
>
.
7
)
[
1
8
]
.
A
l
s
o
,
t
h
e
t
e
s
t
p
r
e
s
e
n
t
s
g
o
o
d
r
e
l
i
a
b
i
l
i
t
y
f
o
r
t
h
e
c
o
n
s
t
r
u
c
t
s
.
T
h
e
n
,
h
e
l
p
u
s
t
o
t
e
s
t
t
h
e
f
a
c
t
o
r
s
i
n
t
h
e
c
l
a
s
s
i
c
l
i
n
e
a
r
r
e
g
r
e
s
s
i
o
n
m
o
d
e
l
.
3
.
2
.
4
.
Cla
s
s
ic
lin
ea
r
re
g
re
s
s
i
o
n m
o
del
A
class
ical
l
in
ea
r
r
eg
r
ess
io
n
m
o
d
el
was u
s
ed
to
ass
ess
th
e
co
n
s
tr
u
cts
[
2
5
]
.
T
h
e
m
o
d
el
esti
m
atio
n
was
d
ev
elo
p
e
d
u
s
in
g
o
r
d
in
ar
y
leas
t
s
q
u
ar
es
r
eg
r
ess
io
n
(
OL
S)
[
2
6
]
.
B
ef
o
r
e
th
e
OL
S
was
ap
p
lied
,
th
e
n
o
r
m
ality
o
f
th
e
d
ata
was c
o
n
f
ir
m
ed
u
s
in
g
a
P
-
P p
lo
t w
ith
th
e
Ko
lm
o
g
o
r
o
v
‒
Sm
ir
n
o
v
(
K
–
S)
test
[
2
7
]
.
T
h
e
r
esu
lts
s
h
o
wed
a
n
o
r
m
al
d
is
tr
ib
u
tio
n
an
d
n
o
o
u
tlier
s
(
-
3
,
0
m
in
im
u
m
an
d
2
,
5
m
ax
im
u
m
)
.
T
h
e
m
o
d
el
p
r
e
s
en
ted
th
e
v
ar
iab
les
en
ter
ed
(
s
p
atial,
p
lan
et,
p
r
o
f
it,
p
eo
p
le
,
an
d
cu
ltu
r
al)
as
in
d
ep
e
n
d
en
t
v
ar
ia
b
les
an
d
(
g
o
v
er
n
an
ce
)
as
th
e
d
ep
en
d
en
t
v
ar
iab
le.
All
th
e
r
eq
u
ested
v
ar
iab
les
wer
e
en
ter
ed
.
T
h
e
i
n
d
e
p
en
d
en
ce
d
iag
n
o
s
is
(
n
o
n
a
u
to
c
o
r
r
elate
d
r
esid
u
als)
was te
s
ted
u
s
in
g
th
e
Du
r
b
in
-
W
atso
n
test
an
d
s
h
o
wed
a
s
ig
n
if
ican
t
d
if
f
er
en
ce
b
etwe
en
1
,
5
an
d
2
,
5
an
d
n
ea
r
2
,
0
(
1
,
6
6
0
,
Sig
<
.
0
0
1
)
.
T
h
e
R
2
in
d
icate
d
th
at
th
e
v
a
r
iatio
n
was
(
6
7
2
)
o
r
6
7
%.
Fo
llo
win
g
t
h
e
h
o
m
o
s
ce
d
asti
city
d
iag
n
o
s
tic
test
,
th
e
r
esu
lts
s
h
o
w
h
o
m
o
s
ce
d
asti
city
,
with
a
s
eq
u
en
ce
o
f
r
a
n
d
o
m
v
ar
ia
b
les
[
2
8
]
.
I
n
ter
m
s
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
13
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
1
7
8
-
4
1
8
5
4182
m
u
ltico
llin
ea
r
ity
[
2
9
]
,
th
e
r
esu
lts
wer
e
co
n
s
is
ten
t
with
th
o
s
e
o
f
th
e
v
ar
ia
n
ce
in
f
latio
n
f
ac
t
o
r
(
VI
F
)
an
d
to
ler
an
ce
an
aly
s
es:
p
eo
p
le
(
VI
F
2
,
3
7
9
/t
o
ler
an
ce
,
4
2
0
)
;
p
la
n
et
(
VI
F
1
,
9
1
3
/to
ler
an
ce
,
5
2
3
)
;
p
r
o
f
it
(
V
I
F
2
,
2
6
2
/to
le
r
an
ce
,
4
4
2
)
;
cu
ltu
r
al
(
VI
F
3
,
7
1
8
/to
l
er
an
ce
,
2
6
9
)
;
an
d
s
p
atial
(
VI
F
3
,
7
3
4
/to
ler
an
ce
,
2
6
8
)
.
T
h
e
co
n
s
tr
u
cts
th
at
b
est
r
ep
r
esen
ted
th
e
m
o
d
el
in
ter
m
s
o
f
ex
p
lan
at
o
r
y
im
p
o
r
tan
ce
(
β)
wer
e
p
lan
et,
p
r
o
f
it a
n
d
cu
lt
u
r
e.
3
.
2
.
5
.
Art
if
icia
l
neura
l net
wo
rk
mo
del
T
h
e
m
o
d
el
was
d
ev
elo
p
ed
to
c
o
n
f
ir
m
t
h
e
s
ec
o
n
d
tim
e
th
e
c
o
n
s
tr
u
cts
wer
e
ass
ess
ed
[
2
5
]
.
A
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
(
ML
P)
was
u
s
ed
as
a
tech
n
iq
u
e.
I
n
a
n
e
u
r
al
n
etwo
r
k
,
th
e
v
ar
ia
b
les
ar
e
r
an
d
o
m
ly
s
elec
ted
f
o
r
tr
ain
in
g
an
d
test
in
g
[
3
0
]
.
T
h
e
s
u
m
m
a
r
y
o
f
ca
s
e
p
r
o
ce
s
s
in
g
was
co
m
p
o
s
ed
o
f
2
2
8
.
69
.
5
%
(
tr
ain
i
n
g
)
a
n
d
1
0
0
.
30
.
5
%
(
test
in
g
)
,
f
o
r
a
to
tal
o
f
3
2
8
v
alid
r
esp
o
n
s
es
(
1
0
0
%).
T
h
e
n
etwo
r
k
was
b
u
ilt
b
ased
o
n
s
ev
er
al
ch
ar
ac
ter
is
tics
.
T
h
e
in
p
u
t
lay
e
r
was
co
m
p
o
s
ed
b
y
f
iv
e
v
ar
iab
les:
p
e
o
p
le,
p
r
o
f
it,
p
lan
et,
cu
ltu
r
al
,
an
d
s
p
atial
.
T
h
e
o
u
tp
u
t
lay
e
r
r
ep
r
esen
ts
th
e
m
o
d
el'
s
d
ep
en
d
en
t v
ar
iab
le,
Go
v
er
n
a
n
ce
.
T
h
e
m
o
d
el
was a
p
p
r
o
ac
h
ed
b
y
h
id
in
g
th
e
b
ed
an
d
th
e
h
y
p
er
b
o
lic
tan
g
en
t
ac
tin
g
o
n
t
h
e
ac
tiv
atio
n
f
u
n
ctio
n
,
in
ter
v
a
l
(
1
,
1
)
.
T
h
e
n
e
u
r
al
n
etwo
r
k
w
as
m
ea
s
u
r
ed
b
y
th
e
er
r
o
r
f
u
n
ctio
n
[
2
9
]
.
T
h
e
s
y
n
a
p
tic
weig
h
ts
th
at
ex
p
lain
th
e
v
ar
iab
les
ass
o
ciate
d
with
th
e
ap
p
r
o
p
r
iate
n
e
u
r
al
n
etwo
r
k
s
ettin
g
s
ar
e
s
h
o
wn
in
Fig
u
r
e
2
.
Ad
d
itio
n
ally
,
a
m
ath
em
atica
l
d
escr
ip
tio
n
o
f
an
ar
tific
ial
n
eu
r
al
n
etwo
r
k
is
p
r
esen
ted
in
th
e
f
o
llo
win
g
f
o
r
m
u
la:
Y=
f
(
o
)
(W
(
L
)
⋅
f
(
L
−
1)
(
f
(2)
(W
(2)
⋅
f
(
1)
(W
(1)
⋅
X+
b
(1)
)
+b
(2)
)
)
+b
(
L
)
)
wh
er
e
X
is
th
e
in
p
u
t
d
ata
,
L
is
th
e
n
u
m
b
er
o
f
lay
er
s
,
W
(
i
)
r
ep
r
esen
ts
th
e
weig
h
t
m
atr
ix
f
o
r
th
e
co
n
n
ec
tio
n
s
b
etwe
en
th
e
i
th
a
n
d
(
i
−
1
)
th
la
y
er
s
,
b
(
i
)
th
e
b
ias
v
ec
to
r
f
o
r
t
h
e
i
th
lay
er
,
f
(
i
)
is
th
e
ac
tiv
atio
n
f
u
n
ctio
n
ap
p
lied
at
th
e
i
th
lay
er
,
a
n
d
Y
is
th
e
u
t
p
u
td
ata.
Fig
u
r
e
2
.
Flo
wch
ar
t
o
f
th
e
AI
-
b
ased
m
o
d
els an
d
ex
p
e
r
im
en
t
al
m
eth
o
d
s
ap
p
lied
T
h
e
T
ab
le
2
s
h
o
w
t
h
e
r
esu
lts
o
f
th
e
p
r
ed
icted
m
o
d
e
.
T
h
e
p
r
ed
icted
in
p
u
t
lay
e
r
v
alu
es
wer
e
p
r
o
ce
s
s
ed
u
s
in
g
a
s
tan
d
ar
d
ized
ap
p
r
o
ac
h
b
etwe
en
-
1
an
d
1
,
an
ass
o
ciatio
n
v
alu
e.
I
n
ter
m
s
o
f
th
e
p
r
ed
ict
ed
er
r
o
r
,
th
e
m
o
d
el
ass
u
m
es
a
v
alu
e
o
f
3
5
5
(
3
5
%),
wh
ich
,
in
ad
d
itio
n
to
b
ein
g
co
n
s
id
er
ed
r
elativ
ely
lo
w,
d
e
m
o
n
s
tr
ates
h
o
w
t
h
e
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
ig
n
if
ican
tly
p
r
ed
icts
th
e
Go
v
er
n
an
ce
v
ar
iab
le.
Fo
r
t
h
e
v
alid
a
tio
n
o
f
th
e
m
o
d
el
p
r
esen
ted
,
Fig
u
r
es
3
a
n
d
4
s
h
o
w
th
e
b
e
h
av
io
r
o
f
th
e
p
r
ed
ic
ted
v
alu
e,
tak
in
g
in
to
ac
co
u
n
t
th
e
r
esid
u
al
v
alu
e
.
T
h
e
lin
ea
r
ity
o
f
th
e
p
r
ed
icte
d
v
alu
es
to
th
e
o
b
s
er
v
ed
v
alu
es
ca
n
b
e
s
ee
n
in
Fig
u
r
e
3
,
ac
c
o
r
d
in
g
to
th
e
lin
ea
r
ar
r
an
g
em
e
n
t o
f
t
h
e
p
o
i
n
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Da
ta
-
d
r
iven
d
ec
is
io
n
s
:
A
r
tifi
cia
l in
tellig
en
ce
-
b
a
s
ed
ex
p
eri
men
ta
l v
a
lid
a
tio
n
o
f
…
(
R
o
n
n
i
e
F
ig
u
eired
o
)
4183
T
ab
le
2
.
Sy
n
a
p
tic
weig
h
ts
(
p
ar
am
eter
e
s
tim
ates)
o
f
th
e
p
r
e
d
i
cted
m
o
d
es
F
o
r
e
c
a
st
P
r
e
d
i
c
t
o
r
H
i
d
d
e
n
L
a
y
e
r
1
O
u
t
p
u
t
L
a
y
e
r
I
n
p
u
t
L
a
y
e
r
H
(
1
:
1
)
H
(
1
:
2
)
H
(
1
:
3
)
G
O
V
ER
N
A
N
C
E
(
B
i
a
s)
.
6
1
3
.
4
4
0
.
6
4
9
P
EO
P
LE
-
.
4
1
5
-
.
6
7
3
-
.
2
6
7
P
LA
N
ET
-
.
1
1
6
-
.
2
7
8
.
9
6
2
P
R
O
F
I
T
-
.
5
3
8
-
.
2
3
8
.
1
1
3
C
U
L
TU
R
A
L
-
.
5
2
7
-
.
5
5
1
.
2
6
8
S
P
A
TI
A
L
-
.
0
8
7
-
.
2
8
3
-
.
0
0
3
H
i
d
d
e
n
L
a
y
e
r
1
(
B
i
a
s)
-
.
3
0
0
H
(
1
:
1
)
-
.
3
1
0
H
(
1
:
2
)
-
.
0
3
8
H
(
1
:
3
)
.
9
6
3
Fig
u
r
e
3
.
Diag
r
a
m
o
f
p
r
ed
icte
d
v
alu
es
Fig
u
r
e
4
.
Diag
r
a
m
o
f
th
e
r
esid
u
als p
er
p
r
e
d
ictio
n
C
o
n
s
i
d
e
r
i
n
g
t
h
e
c
o
n
t
r
i
b
u
t
i
o
n
o
f
t
h
e
i
n
d
e
p
e
n
d
e
n
t
v
a
r
i
a
b
l
e
s
t
o
t
h
e
m
o
d
e
l
c
o
n
s
t
r
u
c
t
i
o
n
,
t
h
e
p
l
a
n
e
t
c
o
n
s
t
r
u
c
t
i
s
t
h
e
m
o
s
t
r
e
p
r
e
s
e
n
t
a
t
i
v
e
o
f
th
e
n
e
t
w
o
r
k
i
n
t
e
r
m
s
o
f
p
r
e
d
i
c
t
a
b
i
l
it
y
,
w
i
t
h
a
v
a
l
u
e
o
f
.
4
9
1
(
4
9
%
)
,
f
o
l
l
o
w
e
d
b
y
c
u
l
t
u
r
a
l
,
w
it
h
a
v
a
l
u
e
o
f
.
2
5
5
(
2
5
%
)
;
p
r
o
f
i
t
,
w
i
t
h
a
v
a
l
u
e
o
f
.
1
4
5
(
1
4
%
)
;
p
e
o
p
l
e
,
w
i
t
h
a
v
a
l
u
e
o
f
,
0
8
8
(
8
%
)
;
a
n
d
S
P
A
T
I
A
L
,
w
it
h
a
v
a
l
u
e
o
f
,
0
2
1
(
2
%
)
.
W
i
t
h
r
e
g
a
r
d
t
o
t
h
e
r
e
l
ev
a
n
c
e
o
f
t
h
e
d
i
m
e
n
s
i
o
n
f
o
r
t
h
e
m
o
d
e
l
,
t
h
e
t
r
a
i
n
i
n
g
a
n
d
t
e
s
t
v
al
u
e
s
s
h
o
w
t
h
a
t
t
h
e
P
L
A
N
E
T
c
o
n
s
t
r
u
c
t
w
as
1
0
0
%
.
W
h
i
l
e
t
h
e
o
t
h
e
r
c
o
n
s
t
r
u
c
t
s
we
r
e
u
s
e
d
a
s
f
o
ll
o
ws
:
c
u
l
t
u
r
a
l
(
5
1
.
9
%
)
,
p
r
o
f
i
t
(
2
9
.
6
%)
,
p
e
o
p
l
e
(
1
7
.
9
%
)
,
a
n
d
s
p
a
t
i
al
(
4
.
2
%
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
13
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
1
7
8
-
4
1
8
5
4184
4.
DIS
CU
SS
I
O
N
R
ec
en
t
s
tu
d
ies
o
n
ec
o
s
y
s
tem
s
er
v
ices
s
tu
d
ies
s
h
o
w
th
at
d
ee
p
lear
n
in
g
is
ch
an
g
in
g
th
e
way
o
f
d
ec
is
io
n
s
ar
e
tak
in
g
.
T
h
is
s
tu
d
y
in
v
esti
g
ated
h
o
w
ca
n
we
in
cr
ea
s
e
th
e
s
u
s
tain
ab
le
d
ec
is
io
n
s
o
f
o
ce
an
ec
o
s
y
s
tem
s
er
v
ices
g
o
v
er
n
an
ce
.
W
h
ite
r
ec
en
t
s
tu
d
ies
f
o
cu
s
ed
o
n
d
etec
tio
n
o
f
r
o
c
k
f
is
h
in
c
h
allen
g
in
g
u
n
d
er
wate
r
en
v
ir
o
n
m
e
n
ts
[
4
]
,
d
etec
tio
n
o
f
co
astal
er
o
s
io
n
[
5
]
an
d
s
o
il
ty
p
e
p
r
e
d
ictio
n
[
6
]
,
th
ey
h
av
e
n
o
t
ex
p
licitly
ad
d
r
e
s
s
ed
its
s
u
p
p
o
r
t
th
e
g
o
v
er
n
an
ce
o
f
o
ce
a
n
ec
o
s
s
y
tem
s
s
er
v
ices in
cr
ea
s
e
th
e
v
alu
e
o
f
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
es
.
W
e
f
o
u
n
d
th
at
r
elatio
n
s
h
ip
s
b
etwe
en
s
ix
v
a
r
iab
les
an
d
f
ac
to
r
s
m
ea
s
u
r
em
en
t
s
u
s
tain
ab
le
g
o
v
er
n
a
n
ce
d
ec
is
io
n
s
in
o
ce
an
ec
o
s
y
s
tem
s
er
v
ice.
T
h
e
v
ar
iab
les
c
o
r
r
elate
d
,
ex
p
lain
,
an
d
v
alid
ate
s
ix
co
n
s
tr
u
cts,
lik
e
g
o
v
er
n
an
ce
,
p
eo
p
le,
p
lan
et,
p
r
o
f
it,
c
u
ltu
r
al
,
a
n
d
s
p
atitial.
W
e
f
o
u
n
d
f
i
v
e
in
d
e
p
en
d
e
n
t
v
ar
iab
les
an
d
o
n
e
d
ep
en
d
e
n
t v
ar
iab
le
(
g
o
v
er
n
a
n
ce
)
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
s
s
h
o
w
t
h
at
th
e
s
am
e
v
ar
iab
les
ar
e
co
r
r
elate
d
in
ter
m
s
o
f
r
esu
lts
.
I
ts
m
ea
n
th
at,
th
e
r
esu
lts
in
ar
tific
ial
n
eu
r
al
n
etwo
r
k
p
r
esen
t
th
e
v
ar
iab
le
s
“p
lan
et”,
“c
u
ltu
r
al”
,
an
d
“p
r
o
f
it”
as
th
e
m
ain
co
n
tr
ib
u
tio
n
.
W
h
ile
in
class
ical
lin
ea
r
r
eg
r
ess
io
n
,
th
e
im
p
o
r
tan
ce
o
f
v
ar
ia
b
les
was
“p
lan
et”,
“c
u
ltu
r
al”
,
a
n
d
“p
r
o
f
it”.
T
h
e
o
th
er
s
ch
a
n
g
e
in
ter
m
s
o
f
s
eq
u
en
ce
,
b
u
t
th
e
v
a
r
i
ab
les
s
till
th
e
s
am
e
in
b
o
th
tech
n
iq
u
es
ap
p
lied
.
I
ts
h
elp
to
g
o
v
e
r
n
an
ce
o
f
o
ce
an
ec
o
s
y
s
tem
s
b
e
ad
eq
u
ate
an
d
ef
f
ec
tiv
e
in
ter
m
s
o
f
m
an
a
g
e
m
en
t
ef
f
icien
cy
to
s
u
s
tain
ab
le
d
ec
is
io
n
s
.
Fu
tu
r
e
s
tu
d
ies
m
ay
ex
p
l
o
r
e
th
e
s
ca
le
in
d
if
f
er
en
t
a
p
p
licatio
n
s
o
f
ec
o
s
y
s
tem
s
er
v
ices.
I
n
ad
d
itio
n
,
a
m
o
d
el
with
s
ca
le
an
d
f
ac
to
r
s
c
o
u
ld
b
e
d
ev
elo
p
m
en
t t
o
m
ea
s
u
r
e
th
e
d
ec
is
io
n
-
m
a
k
in
g
p
r
o
ce
s
s
in
o
th
e
r
c
o
u
n
tr
ies
in
E
u
r
o
p
e
o
r
o
u
ts
id
e.
I
n
ad
d
i
tio
n
,
s
tu
d
ies
ca
n
in
clu
d
e
a
n
ew
v
ar
iab
le
cr
ea
te
o
th
er
ap
p
r
o
ac
h
es.
Fin
ally
,
th
e
s
o
lu
tio
n
s
p
r
o
p
o
s
ed
co
u
l
d
b
e
te
s
ted
with
an
o
th
er
ar
tific
ial
in
te
llig
en
ce
tech
n
o
lo
g
y
.
5.
CO
NCLU
SI
O
N
T
h
e
u
s
e
o
f
ar
tific
ial
n
eu
r
al
n
et
wo
r
k
s
(
d
ee
p
lear
n
in
g
)
c
o
m
b
in
ed
with
class
ical
lin
ea
r
r
eg
r
ess
io
n
h
elp
e
d
to
v
alid
ate
th
e
d
ec
is
io
n
s
ca
le
f
o
r
o
ce
an
ec
o
s
y
s
tem
s
er
v
ices,
g
u
ar
an
teein
g
a
s
o
lu
tio
n
f
o
r
g
o
v
er
n
an
ce
in
ter
m
s
o
f
f
u
tu
r
e
d
ec
is
io
n
s
.
E
n
s
u
r
in
g
th
e
r
eliab
ilit
y
o
f
th
e
s
ca
le
b
ec
am
e
a
co
n
ce
r
n
d
u
e
to
t
h
e
n
u
m
b
e
r
o
f
f
ac
to
r
s
an
d
th
e
co
m
p
lex
ity
o
f
th
e
p
r
o
ce
s
s
,
f
r
o
m
its
in
itial
p
h
ase
d
ed
icate
d
to
co
n
s
tr
u
ctin
g
th
e
f
ac
to
r
s
.
I
n
ad
d
itio
n
to
co
n
s
id
er
in
g
th
e
f
ea
s
ib
ilit
y
o
f
s
ca
lin
g
th
r
o
u
g
h
d
ee
p
lear
n
in
g
ass
o
ciate
d
with
th
e
cl
ass
ic
lin
ea
r
r
eg
r
ess
io
n
tech
n
iq
u
e,
th
is
s
tu
d
y
r
ein
f
o
r
ce
s
th
e
im
p
o
r
tan
ce
o
f
p
r
ed
ictin
g
d
ec
is
io
n
s
,
cr
ea
tin
g
a
p
r
e
d
ictiv
e
ap
p
r
o
ac
h
to
f
o
r
ec
ast
p
o
s
s
ib
le
o
u
tco
m
es
b
ased
o
n
t
h
e
d
ec
is
io
n
s
o
f
v
a
r
io
u
s
k
e
y
d
ec
is
io
n
s
-
m
ak
er
s
.
T
h
e
a
p
p
licatio
n
o
f
d
ec
is
io
n
s
ca
lin
g
to
o
ce
an
ec
o
s
y
s
tem
s
er
v
ices
ca
n
b
e
co
n
s
id
er
ed
a
u
s
ef
u
l
way
o
f
in
c
r
ea
s
in
g
th
e
ass
er
tiv
en
ess
o
f
d
ec
is
io
n
s
,
as
it
ca
n
s
ig
n
if
ican
tly
r
ed
u
ce
th
e
tim
e
i
n
v
ested
in
d
ec
is
io
n
-
m
ak
in
g
d
i
s
cu
s
s
io
n
s
b
y
g
o
v
er
n
an
ce
.
F
UNDING
ACK
NO
W
L
E
D
G
E
M
E
NT
ST
A
T
E
M
E
N
T
T
h
is
wo
r
k
is
f
in
an
ce
d
b
y
n
atio
n
al
f
u
n
d
in
g
th
r
o
u
g
h
th
e
FC
T
—
Fu
n
d
aç
ão
p
a
r
a
a
C
iên
cia
e
a
T
ec
n
o
lo
g
ia,
I
.
P.,
u
n
d
er
th
e
p
r
o
ject
“UI
DB
/0
4
6
3
0
/
2
0
2
0
(
g
r
an
t n
u
m
b
er
)
.
RE
F
E
R
E
NC
E
S
[
1
]
B
.
H
a
a
s
e
t
a
l
.
,
“
Th
e
f
u
t
u
r
e
o
f
o
c
e
a
n
g
o
v
e
r
n
a
n
c
e
,
”
Re
v
i
e
w
s
i
n
Fi
sh
Bi
o
l
o
g
y
a
n
d
Fi
s
h
e
r
i
e
s
,
v
o
l
.
3
2
,
n
o
.
1
,
p
p
.
2
5
3
–
2
7
0
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
1
6
0
-
020
-
0
9
6
3
1
-
x.
[
2
]
N
.
M
e
j
j
a
d
a
n
d
M
.
R
o
v
e
r
e
,
“
U
n
d
e
r
s
t
a
n
d
i
n
g
t
h
e
I
mp
a
c
t
s
o
f
b
l
u
e
e
c
o
n
o
my
g
r
o
w
t
h
o
n
d
e
e
p
-
s
e
a
e
c
o
s
y
st
e
m
serv
i
c
e
s,”
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
3
,
n
o
.
2
2
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
3
2
2
1
2
4
7
8
.
[
3
]
R
.
D
.
C
a
v
a
n
a
g
h
,
S
.
B
r
o
sz
e
i
t
,
G
.
M
.
P
i
l
l
i
n
g
,
S
.
M
.
G
r
a
n
t
,
E
.
J.
M
u
r
p
h
y
,
a
n
d
M
.
C
.
A
u
st
e
n
,
“
V
a
l
u
i
n
g
b
i
o
d
i
v
e
r
s
i
t
y
a
n
d
e
c
o
sy
st
e
m
serv
i
c
e
s
:
a
u
s
e
f
u
l
w
a
y
t
o
m
a
n
a
g
e
a
n
d
c
o
n
ser
v
e
mari
n
e
r
e
so
u
r
c
e
s?,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
R
o
y
a
l
S
o
c
i
e
t
y
B:
B
i
o
l
o
g
i
c
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
2
8
3
,
n
o
.
1
8
4
4
,
D
e
c
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
9
8
/
r
s
p
b
.
2
0
1
6
.
1
6
3
5
.
[
4
]
M
.
Li
u
,
W
.
J
i
a
n
g
,
M
.
H
o
u
,
Z.
Q
i
,
R
.
Li
,
a
n
d
C
.
Z
h
a
n
g
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
o
f
r
o
c
k
f
i
sh
i
n
c
h
a
l
l
e
n
g
i
n
g
u
n
d
e
r
w
a
t
e
r
e
n
v
i
r
o
n
me
n
t
s,”
Fr
o
n
t
i
e
rs
i
n
M
a
ri
n
e
S
c
i
e
n
c
e
,
v
o
l
.
1
0
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
mars
.
2
0
2
3
.
1
2
4
2
0
4
1
.
[
5
]
R
.
D
.
V
.
-
S
a
l
a
z
a
r
e
t
a
l
.
,
“
D
e
t
e
c
t
i
o
n
o
f
c
o
a
s
t
a
l
e
r
o
si
o
n
a
n
d
p
r
o
g
r
a
d
a
t
i
o
n
i
n
t
h
e
c
o
l
o
m
b
i
a
n
‘
A
t
r
a
t
o
R
i
v
e
r
’
d
e
l
t
a
b
y
u
si
n
g
se
n
t
i
n
e
l
-
1
sy
n
t
h
e
t
i
c
a
p
e
r
t
u
r
e
r
a
d
a
r
d
a
t
a
,
”
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
6
,
n
o
.
3
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
6
0
3
0
5
5
2
.
[
6
]
S
u
w
a
r
d
i
e
t
a
l
.
,
“
O
p
t
i
m
i
z
a
t
i
o
n
o
f
a
s
o
i
l
t
y
p
e
p
r
e
d
i
c
t
i
o
n
m
e
t
h
o
d
b
a
se
d
o
n
t
h
e
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
a
n
d
v
e
g
e
t
a
t
i
o
n
c
h
a
r
a
c
t
e
r
i
st
i
c
s
,
”
Pl
a
n
t
S
c
i
e
n
c
e
T
o
d
a
y
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
4
7
1
9
/
p
s
t
.
2
9
2
6
.
[
7
]
B
.
A
l
m
e
i
d
a
a
n
d
P
.
C
a
b
r
a
l
,
“
A
h
y
b
r
i
d
mo
d
e
l
l
i
n
g
a
p
p
r
o
a
c
h
f
o
r
d
e
t
e
c
t
i
n
g
se
a
s
o
n
a
l
v
a
r
i
a
t
i
o
n
s
i
n
i
n
l
a
n
d
g
r
e
e
n
-
b
l
u
e
e
c
o
s
y
s
t
e
m
s,”
Re
m
o
t
e
S
e
n
si
n
g
A
p
p
l
i
c
a
t
i
o
n
s:
S
o
c
i
e
t
y
a
n
d
E
n
v
i
r
o
n
m
e
n
t
,
v
o
l
.
3
3
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
sas
e
.
2
0
2
3
.
1
0
1
1
2
1
.
[
8
]
A
.
S
u
g
i
m
o
t
o
,
H
.
S
u
g
i
n
o
,
a
n
d
J.
H
o
r
i
,
“
H
o
w
b
o
u
n
t
i
f
u
l
i
s
t
h
e
o
c
e
a
n
?
P
a
r
t
i
c
i
p
a
t
o
r
y
v
a
l
u
a
t
i
o
n
o
f
h
u
ma
n
–
n
a
t
u
r
e
r
e
l
a
t
i
o
n
s
h
i
p
s
i
n
Y
a
e
y
a
m
a
I
s
l
a
n
d
s
,
O
k
i
n
a
w
a
,
J
a
p
a
n
,
”
S
u
s
t
a
i
n
a
b
i
l
i
t
y
S
c
i
e
n
c
e
,
v
o
l
.
1
7
,
n
o
.
3
,
p
p
.
8
7
9
–
8
9
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
6
2
5
-
0
2
1
-
0
0
9
9
4
-
z.
[
9
]
F
.
J.
S
i
j
t
sm
a
,
N
.
M
e
h
n
e
n
,
P
.
A
n
g
e
l
st
a
m,
a
n
d
J.
M
u
ñ
o
z
-
R
o
j
a
s
,
“
M
u
l
t
i
-
sca
l
e
ma
p
p
i
n
g
o
f
c
u
l
t
u
r
a
l
e
c
o
sy
s
t
e
m
ser
v
i
c
e
s
i
n
a
so
c
i
o
-
e
c
o
l
o
g
i
c
a
l
l
a
n
d
s
c
a
p
e
:
a
c
a
s
e
st
u
d
y
o
f
t
h
e
i
n
t
e
r
n
a
t
i
o
n
a
l
w
a
d
d
e
n
s
e
a
r
e
g
i
o
n
,
”
L
a
n
d
sc
a
p
e
Ec
o
l
o
g
y
,
v
o
l
.
3
4
,
n
o
.
7
,
p
p
.
1
7
5
1
–
1
7
6
8
,
J
u
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
9
8
0
-
0
1
9
-
0
0
8
4
1
-
8.
[
1
0
]
L.
S
c
h
u
l
t
z
,
C
.
F
o
l
k
e
,
H
.
Ö
st
e
r
b
l
o
m,
a
n
d
P
.
O
l
ss
o
n
,
“
A
d
a
p
t
i
v
e
g
o
v
e
r
n
a
n
c
e
,
e
c
o
s
y
st
e
m
ma
n
a
g
e
me
n
t
,
a
n
d
n
a
t
u
r
a
l
c
a
p
i
t
a
l
,
”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
N
a
t
i
o
n
a
l
Ac
a
d
e
m
y
o
f
S
c
i
e
n
c
e
s
,
v
o
l
.
1
1
2
,
n
o
.
2
4
,
p
p
.
7
3
6
9
–
7
3
7
4
,
Ju
n
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
7
3
/
p
n
a
s
.
1
4
0
6
4
9
3
1
1
2
.
[
1
1
]
R
.
F
i
g
u
e
i
r
e
d
o
a
n
d
P
.
C
a
b
r
a
l
,
“
O
c
e
a
n
e
c
o
s
y
st
e
m
ser
v
i
c
e
s
:
m
o
d
e
l
i
n
g
a
f
a
c
t
o
r
d
e
v
e
l
o
p
me
n
t
p
r
o
c
e
ss
t
o
c
r
e
a
t
e
su
st
a
i
n
a
b
l
e
v
a
l
u
e
f
o
r
d
e
c
i
si
o
n
s,
”
S
u
s
t
a
i
n
a
b
i
l
i
t
y
Ac
c
o
u
n
t
i
n
g
,
Ma
n
a
g
e
m
e
n
t
a
n
d
P
o
l
i
c
y
J
o
u
rn
a
l
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
8
/
S
A
M
P
J
-
09
-
2023
-
0
7
0
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Da
ta
-
d
r
iven
d
ec
is
io
n
s
:
A
r
tifi
cia
l in
tellig
en
ce
-
b
a
s
ed
ex
p
eri
men
ta
l v
a
lid
a
tio
n
o
f
…
(
R
o
n
n
i
e
F
ig
u
eired
o
)
4185
[
1
2
]
E.
G
.
Tr
e
v
e
l
y
a
n
a
n
d
P
.
N
.
R
o
b
i
n
s
o
n
,
“
D
e
l
p
h
i
m
e
t
h
o
d
o
l
o
g
y
i
n
h
e
a
l
t
h
r
e
se
a
r
c
h
:
h
o
w
t
o
d
o
i
t
?
,
”
Eu
r
o
p
e
a
n
J
o
u
r
n
a
l
o
f
I
n
t
e
g
r
a
t
i
v
e
Me
d
i
c
i
n
e
,
v
o
l
.
7
,
n
o
.
4
,
p
p
.
4
2
3
–
4
2
8
,
A
u
g
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
u
j
i
m.
2
0
1
5
.
0
7
.
0
0
2
.
[
1
3
]
R
.
Lo
o
,
“
Th
e
d
e
l
p
h
i
me
t
h
o
d
:
a
p
o
w
e
r
f
u
l
t
o
o
l
f
o
r
st
r
a
t
e
g
i
c
ma
n
a
g
e
m
e
n
t
,
”
P
o
l
i
c
i
n
g
:
A
n
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Po
l
i
c
e
S
t
r
a
t
e
g
i
e
s
&
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
2
5
,
n
o
.
4
,
p
p
.
7
6
2
–
7
6
9
,
D
e
c
.
2
0
0
2
,
d
o
i
:
1
0
.
1
1
0
8
/
1
3
6
3
9
5
1
0
2
1
0
4
5
0
6
7
7
.
[
1
4
]
P
.
N
.
M
u
c
h
i
r
i
,
L.
P
i
n
t
e
l
o
n
,
H
.
M
a
r
t
i
n
,
a
n
d
A
.
-
M
.
D
.
M
e
y
e
r
,
“
E
mp
i
r
i
c
a
l
a
n
a
l
y
si
s
o
f
ma
i
n
t
e
n
a
n
c
e
p
e
r
f
o
r
ma
n
c
e
mea
su
r
e
me
n
t
i
n
B
e
l
g
i
a
n
i
n
d
u
st
r
i
e
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Pro
d
u
c
t
i
o
n
Re
se
a
r
c
h
,
v
o
l
.
4
8
,
n
o
.
2
0
,
p
p
.
5
9
0
5
–
5
9
2
4
,
O
c
t
.
2
0
1
0
,
d
o
i
:
1
0
.
1
0
8
0
/
0
0
2
0
7
5
4
0
9
0
3
1
6
0
7
6
6
.
[
1
5
]
I
.
Et
i
k
a
n
,
“
C
o
m
p
a
r
i
si
o
n
o
f
s
n
o
w
b
a
l
l
s
a
mp
l
i
n
g
a
n
d
se
q
u
e
n
t
i
a
l
sam
p
l
i
n
g
t
e
c
h
n
i
q
u
e
,
”
Bi
o
m
e
t
ri
c
s
&
B
i
o
s
t
a
t
i
st
i
c
s
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
,
v
o
l
.
3
,
n
o
.
1
,
J
a
n
.
2
0
1
6
,
d
o
i
:
1
0
.
1
5
4
0
6
/
b
b
i
j
.
2
0
1
6
.
0
3
.
0
0
0
5
5
.
[
1
6
]
G
.
F
r
a
n
k
e
a
n
d
M
.
S
a
r
st
e
d
t
,
“
H
e
u
r
i
st
i
c
s
v
e
r
s
u
s
st
a
t
i
st
i
c
s
i
n
d
i
scr
i
mi
n
a
n
t
v
a
l
i
d
i
t
y
t
e
s
t
i
n
g
:
A
c
o
m
p
a
r
i
so
n
o
f
f
o
u
r
p
r
o
c
e
d
u
r
e
s
,
”
I
n
t
e
rn
e
t
Re
se
a
rc
h
,
v
o
l
.
2
9
,
n
o
.
3
,
p
p
.
4
3
0
–
4
4
7
,
Ju
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
8
/
I
n
t
R
-
12
-
2
0
1
7
-
0
5
1
5
.
[
1
7
]
F
.
O
.
W
a
l
u
m
b
w
a
,
B
.
J
.
A
v
o
l
i
o
,
W
.
L.
G
a
r
d
n
e
r
,
T.
S
.
W
e
r
n
s
i
n
g
,
a
n
d
S
.
J.
P
e
t
e
r
so
n
,
“
A
u
t
h
e
n
t
i
c
l
e
a
d
e
r
s
h
i
p
:
d
e
v
e
l
o
p
m
e
n
t
a
n
d
v
a
l
i
d
a
t
i
o
n
o
f
a
t
h
e
o
r
y
-
b
a
se
d
me
a
su
r
e
†
,
”
J
o
u
r
n
a
l
o
f
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
3
4
,
n
o
.
1
,
p
p
.
8
9
–
1
2
6
,
F
e
b
.
2
0
0
8
,
d
o
i
:
1
0
.
1
1
7
7
/
0
1
4
9
2
0
6
3
0
7
3
0
8
9
1
3
.
[
1
8
]
R
.
P
.
B
a
g
o
z
z
i
a
n
d
Y
.
Y
i
,
“
S
p
e
c
i
f
i
c
a
t
i
o
n
,
e
v
a
l
u
a
t
i
o
n
,
a
n
d
i
n
t
e
r
p
r
e
t
a
t
i
o
n
o
f
s
t
r
u
c
t
u
r
a
l
e
q
u
a
t
i
o
n
m
o
d
e
l
s,”
J
o
u
rn
a
l
o
f
t
h
e
Ac
a
d
e
m
y
o
f
Ma
r
k
e
t
i
n
g
S
c
i
e
n
c
e
,
v
o
l
.
4
0
,
n
o
.
1
,
p
p
.
8
–
3
4
,
J
a
n
.
2
0
1
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
7
4
7
-
0
1
1
-
0
2
7
8
-
x.
[
1
9
]
N
.
K
r
i
s
h
n
a
mm
a
l
,
C
.
K
a
l
a
i
a
r
a
sa
n
,
a
n
d
A
.
B
h
a
r
a
t
h
i
,
“
M
o
d
e
l
l
i
n
g
a
l
e
a
r
n
i
n
g
-
b
a
se
d
d
y
n
a
m
i
c
t
r
e
e
r
o
u
t
i
n
g
mo
d
e
l
f
o
r
w
i
r
e
l
e
ss
mes
h
a
c
c
e
ss
n
e
t
w
o
r
k
s
,
”
C
o
m
p
u
t
e
r
S
y
s
t
e
m
s
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
4
4
,
n
o
.
2
,
p
p
.
1
5
3
1
–
1
5
4
9
,
2
0
2
3
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
sse
.
2
0
2
3
.
0
2
4
2
5
1
.
[
2
0
]
I
.
B
e
l
e
k
o
u
k
i
a
s,
J.
A
.
G
.
-
R
e
y
e
s
,
a
n
d
V
.
K
u
mar,
“
T
h
e
i
mp
a
c
t
o
f
l
e
a
n
met
h
o
d
s
a
n
d
t
o
o
l
s
o
n
t
h
e
o
p
e
r
a
t
i
o
n
a
l
p
e
r
f
o
r
ma
n
c
e
o
f
man
u
f
a
c
t
u
r
i
n
g
o
r
g
a
n
i
sat
i
o
n
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Pr
o
d
u
c
t
i
o
n
Re
se
a
rch
,
v
o
l
.
5
2
,
n
o
.
1
8
,
p
p
.
5
3
4
6
–
5
3
6
6
,
S
e
p
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
8
0
/
0
0
2
0
7
5
4
3
.
2
0
1
4
.
9
0
3
3
4
8
.
[
2
1
]
A
.
O
d
o
i
,
S
.
W
.
M
a
r
t
i
n
,
P
.
M
i
c
h
e
l
,
D
.
M
i
d
d
l
e
t
o
n
,
J.
H
o
l
t
,
a
n
d
J
.
W
i
l
s
o
n
,
“
I
n
v
e
st
i
g
a
t
i
o
n
o
f
c
l
u
st
e
r
s
o
f
g
i
a
r
d
i
a
s
i
s
u
si
n
g
G
I
S
a
n
d
a
sp
a
t
i
a
l
s
c
a
n
s
t
a
t
i
s
t
i
c
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
H
e
a
l
t
h
G
e
o
g
ra
p
h
i
c
s
,
v
o
l
.
3
,
n
o
.
1
,
2
0
0
4
,
d
o
i
:
1
0
.
1
1
8
6
/
1
4
7
6
-
0
7
2
X
-
3
-
11
.
[
2
2
]
C
.
E
.
L
a
n
c
e
,
M
.
M
.
B
u
t
t
s,
a
n
d
L.
C
.
M
i
c
h
e
l
s
,
“
Th
e
s
o
u
r
c
e
s
o
f
f
o
u
r
c
o
mm
o
n
l
y
r
e
p
o
r
t
e
d
c
u
t
o
f
f
c
r
i
t
e
r
i
a
,
”
O
r
g
a
n
i
za
t
i
o
n
a
l
Re
s
e
a
r
c
h
Me
t
h
o
d
s
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
2
0
2
–
2
2
0
,
A
p
r
.
2
0
0
6
,
d
o
i
:
1
0
.
1
1
7
7
/
1
0
9
4
4
2
8
1
0
5
2
8
4
9
1
9
.
[
2
3
]
F
.
F
a
u
l
,
E.
Er
d
f
e
l
d
e
r
,
A
.
B
u
c
h
n
e
r
,
a
n
d
A
.
-
G
.
L
a
n
g
,
“
S
t
a
t
i
s
t
i
c
a
l
p
o
w
e
r
a
n
a
l
y
s
e
s
u
s
i
n
g
G
*
P
o
w
e
r
3
.
1
:
Te
st
s
f
o
r
c
o
r
r
e
l
a
t
i
o
n
a
n
d
r
e
g
r
e
ss
i
o
n
a
n
a
l
y
ses
,
”
Be
h
a
v
i
o
r
Re
s
e
a
rch
Me
t
h
o
d
s
,
v
o
l
.
4
1
,
n
o
.
4
,
p
p
.
1
1
4
9
–
1
1
6
0
,
N
o
v
.
2
0
0
9
,
d
o
i
:
1
0
.
3
7
5
8
/
B
R
M
.
4
1
.
4
.
1
1
4
9
.
[
2
4
]
G
.
K
.
U
y
a
n
ı
k
a
n
d
N
.
G
ü
l
e
r
,
“
A
st
u
d
y
o
n
mu
l
t
i
p
l
e
l
i
n
e
a
r
r
e
g
r
e
ssi
o
n
a
n
a
l
y
si
s,
”
Pr
o
c
e
d
i
a
-
S
o
c
i
a
l
a
n
d
B
e
h
a
v
i
o
ra
l
S
c
i
e
n
c
e
s
,
v
o
l
.
1
0
6
,
p
p
.
2
3
4
–
2
4
0
,
D
e
c
.
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
b
s
p
r
o
.
2
0
1
3
.
1
2
.
0
2
7
.
[
2
5
]
L.
E
.
E
b
e
r
l
y
,
“
M
u
l
t
i
p
l
e
l
i
n
e
a
r
r
e
g
r
e
ssi
o
n
,
”
i
n
B
i
o
s
t
a
t
i
s
t
i
c
s
,
2
0
0
7
,
p
p
.
1
6
5
–
1
8
7
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
1
-
5
9
7
4
5
-
530
-
5
_
9
.
[
2
6
]
M
.
Tr
a
n
mer
a
n
d
M
.
El
l
i
o
t
,
“
M
u
l
t
i
p
l
e
l
i
n
e
a
r
r
e
g
r
e
ss
i
o
n
,
”
i
n
T
h
e
C
a
t
h
i
e
M
a
rs
h
C
e
n
t
re
f
o
r
C
e
n
su
s
a
n
d
S
u
r
v
e
y
Re
s
e
a
rch
(
C
C
S
R)
,
v
o
l
.
5
,
n
o
.
5
,
p
p
.
1
-
5
,
2
0
0
8
.
[
2
7
]
K
.
F
.
N
i
m
o
n
a
n
d
F
.
L
.
O
sw
a
l
d
,
“
U
n
d
e
r
st
a
n
d
i
n
g
t
h
e
r
e
s
u
l
t
s
o
f
mu
l
t
i
p
l
e
l
i
n
e
a
r
r
e
g
r
e
ss
i
o
n
:
B
e
y
o
n
d
st
a
n
d
a
r
d
i
z
e
d
r
e
g
r
e
ss
i
o
n
c
o
e
f
f
i
c
i
e
n
t
s,
”
O
r
g
a
n
i
za
t
i
o
n
a
l
R
e
se
a
rc
h
M
e
t
h
o
d
s
,
v
o
l
.
1
6
,
n
o
.
4
,
p
p
.
6
5
0
–
6
7
4
,
O
c
t
.
2
0
1
3
,
d
o
i
:
1
0
.
1
1
7
7
/
1
0
9
4
4
2
8
1
1
3
4
9
3
9
2
9
.
[
2
8
]
M
.
K
u
r
u
c
a
n
,
M
.
Ö
z
b
a
l
t
a
n
,
Z.
Y
e
t
g
i
n
,
a
n
d
A
.
A
l
k
a
y
a
,
“
A
p
p
l
i
c
a
t
i
o
n
s
o
f
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
se
d
b
a
t
t
e
r
y
ma
n
a
g
e
me
n
t
s
y
st
e
m
s:
A
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
Re
n
e
w
a
b
l
e
a
n
d
S
u
s
t
a
i
n
a
b
l
e
E
n
e
rg
y
R
e
v
i
e
w
s
,
v
o
l
.
1
9
2
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
ser.
2
0
2
3
.
1
1
4
2
6
2
.
[
2
9
]
M
.
A
l
-
S
h
a
w
w
a
a
n
d
S
.
S
.
A
.
-
N
a
s
e
r
,
“
P
r
e
d
i
c
t
i
n
g
b
i
r
t
h
w
e
i
g
h
t
u
si
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ac
a
d
e
m
i
c
H
e
a
l
t
h
a
n
d
Me
d
i
c
a
l
R
e
se
a
rc
h
(
I
J
AH
MR
)
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
9
–
1
4
,
2
0
1
9
.
[
3
0
]
E.
T.
S
a
y
e
d
,
H
.
R
e
z
k
,
M
.
A
.
A
b
d
e
l
k
a
r
e
e
m,
a
n
d
A
.
G
.
O
l
a
b
i
,
“
A
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
se
d
m
o
d
e
l
l
i
n
g
a
n
d
o
p
t
i
m
i
z
a
t
i
o
n
o
f
mi
c
r
o
a
l
g
a
e
m
i
c
r
o
b
i
a
l
f
u
e
l
c
e
l
l
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
H
y
d
r
o
g
e
n
En
e
rg
y
,
v
o
l
.
5
2
,
p
p
.
1
0
1
5
–
1
0
2
5
,
Jan
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
h
y
d
e
n
e
.
2
0
2
2
.
1
2
.
0
8
1
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ro
n
n
ie
Fi
g
u
e
ire
d
o
is
c
u
tt
in
g
-
e
d
g
e
re
se
a
rc
h
e
r
a
t
th
e
S
c
h
o
o
l
o
f
Tec
h
n
o
l
o
g
y
a
n
d
M
a
n
a
g
e
m
e
n
t,
Ce
n
tre
o
f
A
p
p
li
e
d
Re
se
a
rc
h
in
M
a
n
a
g
e
m
e
n
t
a
n
d
Eco
n
o
m
ics
(CAR
M
E/
F
CT
P
ro
jec
t),
P
o
l
y
tec
h
n
ic
U
n
iv
e
rsit
y
o
f
Leiria.
At
CARME
,
he
h
a
s
b
e
e
n
d
o
in
g
re
se
a
rc
h
in
th
e
f
iel
d
o
f
in
n
o
v
a
ti
o
n
wo
rk
i
n
g
wit
h
d
a
ta
-
d
riv
e
n
in
n
o
v
a
ti
o
n
,
k
n
o
wle
d
g
e
d
isc
o
v
e
ry
i
n
d
a
tab
a
se
s
,
a
n
d
tec
h
-
b
a
se
d
in
n
o
v
a
ti
o
n
.
He
c
a
n
b
e
c
o
n
t
a
c
ted
a
t
e
m
a
il
:
ro
n
n
ie.fi
g
u
e
ired
o
@ip
leiria.p
t
.
Pedro
Ca
b
r
a
l
is
F
u
ll
P
ro
fe
ss
o
r
a
t
Na
n
ji
n
g
Un
i
v
e
rsity
o
f
I
n
f
o
r
m
a
ti
o
n
S
c
ien
c
e
&
Tec
h
n
o
l
o
g
y
in
t
h
e
S
c
h
o
o
l
o
f
Re
m
o
te
S
e
n
sin
g
a
n
d
G
e
o
m
a
ti
c
s
Ap
p
li
c
a
ti
o
n
s
in
Ch
in
a
.
He
h
a
s
d
e
v
e
lo
p
e
d
re
se
a
rc
h
in
th
e
a
re
a
s o
f
G
IS
a
p
p
li
e
d
to
e
c
o
sy
ste
m
se
rv
ice
s.
Cu
rre
n
tl
y
,
h
is f
o
c
u
s
is o
n
th
e
imp
a
c
t
o
f
c
li
m
a
te
-
re
late
d
v
a
ria
b
les
o
n
e
c
o
s
y
ste
m
se
rv
ice
s
u
si
n
g
l
o
n
g
ti
m
e
se
ries
a
n
a
l
y
sis
a
n
d
sc
e
n
a
rio
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
c
a
b
ra
l@n
u
ist.
e
d
u
.
c
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.